Supporting Multi-level Medical Education with Knowledge-Based Systems

Abstract:

Knowledge-based systems for medicine have enjoyed minimal success in developing countries as end-user systems. The reasons for this are complex. As funding agencies understandably tend to err on the side of caution, and knowledge-based systems are still (despite an almost 40 year history) seen as a new and untried technology, few have been implemented. Of those which have, most are inappropriately simple and thus do not fit in with the real-life clinical environment. In contrast to the sophisticated systems in use in developed countries which reflect a mature technology, the use of knowledge-based systems in medicine in developing countries has primarily revolved around simple ‘expert’ systems, where the program functions more as a ‘guru’ than as a support function. We propose the more appropriate use of these systems as educational tools in medicine. In this discussion paper we describe a multi-level programme to support medical education, focusing on patient information systems involving natural language generation, decision-support systems as educational aids for primary health-care workers and model-based reasoning tools which allow exploratory learning for physicans in training. Throughout this paper we refer to Knowledge-Based Medical Education Systems as KBMES.

Keywords:

Medical Education - Knowledge-Based Systems - Developing Countries

• References

• 1 Forster D. Expert Systems in Health for Developing Countries: practice problems and potential. Canada: International Development Research Centre; Report IDRCMR319e 1992
• 2 Forster D. Health Informatics in Developing Countries. London School of Economics: Department of Information Systems. Ph. D. thesis 1990
• 3 Machanik P. Design of medical education software as appropriate technology using Artificial Intelligence and software engineering. University of Witwatersrand: Computer Science Department; Report 88.01 1988
• 4 Machanik P. Software design to meet third world requirements: an experimental software engineering approach. Questionaes Informaticae 1989; 6: 4.
• 5 Korpela M. Nigerian Practice in Computer Systems Development: a multidisciplinary theoretical framework applied to health informatics. Helsinki: Helsinki University of Technology; Ph D. thesis 1994
• 6 Osman L, Abdalla M, Beattie J, Ross S, Russell I, Friend J, Legge J, Graham Douglas J. Reducing hospital admissions through computer supported education for asthma patients. Br Med J 1994; 308: 568-71.
• 7 Binstead K, Cawsey R, Jones R. Generating Personalised Patient Information Using the Medical Record. AIME 95.
• 8 King K. Final project report on AI for Medicine in Developing Countries. University of Edinburgh: Department of Artificial Intelligence; Internal report 1990
• 9 King K. Making Diagnosis Explicit. University of Edinburgh: Department of Artificial Intelligence; Ph. D. thesis 1994
• 10 Clancey WJ, Letsinger R. NEOMYCIN: reconfiguring a rule-based expert system for application to teaching. In: Readings in Medical Artificial Intelligence: the first decade. Addison Wesley; 1984
• 11 Rodolitz NS, Clancey WJ. GUIDON-MANAGE: teaching the process of medical diagnosis. In: Evans D., Patel V. L.. Cognitive Science in Medicine. MIT press; Cambridge Mass.: 1989